INDEX

Explanations

variations of the words "end," "begin," and "for," focusing on their usage in different contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rani

-0.16

ocity

-0.15

geb

-0.15

/Dk

-0.14

ullan

-0.14

ÑıÐ±

-0.14

-pencil

-0.14

icial

-0.14

ÃŃÅ¾

-0.14

amura

-0.14

POSITIVE LOGITS

erland

0.17

èī¦

0.15

gnore

0.14

aign

0.14

ampus

0.14

chy

0.14

cour

0.14

 Fancy

0.14

utsche

0.13

 toReturn

0.13

Activations Density 0.137%

variations of the words "end," "begin," and "for," focusing on their usage in different contexts

No Comments

No Known Activations